WO1994022131A2 - Reconnaissance vocale a detection de pause - Google Patents

Reconnaissance vocale a detection de pause Download PDF

Info

Publication number
WO1994022131A2
WO1994022131A2 PCT/GB1994/000630 GB9400630W WO9422131A2 WO 1994022131 A2 WO1994022131 A2 WO 1994022131A2 GB 9400630 W GB9400630 W GB 9400630W WO 9422131 A2 WO9422131 A2 WO 9422131A2
Authority
WO
WIPO (PCT)
Prior art keywords
recognition
parameter
noise
signal
speech
Prior art date
Application number
PCT/GB1994/000630
Other languages
English (en)
Other versions
WO1994022131A3 (fr
Inventor
Kevin Joseph Power
Stephen Howard Johnson
Francis James Scahill
Simon Patrick Alexander Ringland
John Edward Talintyre
Original Assignee
British Telecommunications Public Limited Company
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by British Telecommunications Public Limited Company filed Critical British Telecommunications Public Limited Company
Priority to AU64330/94A priority Critical patent/AU6433094A/en
Priority to DE69421911T priority patent/DE69421911T2/de
Priority to US08/525,730 priority patent/US5848388A/en
Priority to EP94912002A priority patent/EP0691022B1/fr
Priority to JP52084194A priority patent/JP3691511B2/ja
Priority to CA002158849A priority patent/CA2158849C/fr
Publication of WO1994022131A2 publication Critical patent/WO1994022131A2/fr
Publication of WO1994022131A3 publication Critical patent/WO1994022131A3/fr

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/78—Detection of presence or absence of voice signals
    • G10L25/87—Detection of discrete points within a voice signal
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction

Definitions

  • Speech recognition is used as an input means for control of machines.
  • speech recognition apparatus generally recognises isolated single words.
  • Speech recognition apparatus is also being developed which is intended to recognise multiple words spoken consecutively in a sentence or phrase; this is referred to as connected speech recognition.
  • a microphone picks up a speech signal from a speaker which is then digitised and processed for recognition.
  • the microphone generally also picks up any background or ambient noise and the electrical system between the microphone and the speech recognition apparatus will likewise add noise (e. g. thermal noise, quantising noise and - where the speech is transmitted through a telecommunications channel - line noise).
  • the noise may resemble parts of speech, for example unvoiced sibilant sounds.
  • the correct recognition of a word depends strongly on the ability to distinguish the beginning and the end of the word, which correspond to the end and beginning of noise or silence.
  • the reliability of speech recognition has been shown to depend strongly on the identification of the correct start and end points for speech.
  • One speech processing method which is intended to allow the recognition of a sequence of words using isolated word recognition technology is the "connected - for - isolated” (CFI) technique, described in our co-pending EP patent application 93302538.9 and incorporated herein by reference. This technique assumes that the signal from the microphone will include alternating periods of speech and noise, and attempts to recognise alternately speech and noise.
  • HMM hidden Markov modelling
  • Some types of HMM speech recognition maintain, during recognition, a number of possible state sequences, including a current most probable sequence for defining the word which has been recognised.
  • a CFI recogniser is therefore able to automatically locate the start and end of a word, by maintaining state sequences corresponding to noise, and recognising the sequence of noise - word - noise in the speech signal.
  • many words may include gaps or stops between parts of the word, which might be misrecognised as the end of a word. Accordingly, it is important that the final identification of a word should not take place until the speaker has definitely finished speaking.
  • One method of achieving this is to provide a "time out" after a predetermined time period which can unambiguously be identified as noise. However, we have found that if the period concerned is made long enough to guarantee success, the result is a delay which can be frustratingly . long to the user.
  • One aspect of the invention therefore provides a means of detecting the end of speech for a recogniser of the type in which a most likely state sequence is selected.
  • the invention provides a speech recognition system comprising means for successively generating recognition outputs based on partitioning an input utterance into a speech portion and a following noise portion, characterised by means for detecting the presence of the following noise portion by testing the partitioning using a parameter derived from the input speech signal.
  • the or each parameter is based on the energy of the input speech signal.
  • the parameter comprises a parameter indicating the relative magnitudes of the speech portion and the noise portion indicated by the said partition. Additionally or alternatively, the parameter provides a measure of the variation of the energy of the noise portion according to the partition.
  • the energy is smooth or averaged over several successive time periods, and preferably the averaging is non-linear so as to limit the influence of short spikes of energy differing from the running average.
  • speech recognition apparatus has recognised a word by selecting the most likely possible word, the possibility exists that the recognition was made in error, based either on a similar word (for example one not in the vocabulary of the recogniser) or noise.
  • Means for rejecting the recognition of certain misrecognised words are described in "Rejection of extraneous input in speech recognition applications, using multilayer perceptrons and the trace of HMM's", Mathan and Miclet, 1991 IEEE ICASSP 91 vol 1 pages 93-96, and in “Rejection techniques in continuous speech recognition using hidden Markov models",
  • the object of another aspect of the invention is to provide an improved means for rejecting certain words after they have been identified by a speech recogniser.
  • one aspect of the invention provides a recognition system comprising: input means for receiving a speech signal; recognition processing means for processing the speech signal to indicate its similarity to predetermined patterns to be recognised; output means for supplying a recognition signal indicating recognition of one of said patterns; and rejection means for rejecting the recognition signal under predetermined conditions, characterised in that the rejection means are arranged to receive at least one signal parameter derived from said speech signal which does not depend upon the output of said recognition means.
  • a further aspect of the invention provides a pause detection means, and/or a rejection means, for use in a recogniser employing a variable frame rate.
  • Figure 1 shows schematically an application of a recognition system according to the present invention
  • Figure 2 is a block diagram showing schematically the elements of a recognition processor forming part of Figure 1 according to an embodiment of the invention
  • Figure 3 is a block diagram indicating schematically the components of a classifier forming part of the embodiment of Figure 2;
  • Figure 4 is a flow diagram showing schematically the operation of the classifier of Figure 3;
  • Figure 5 is a block diagram showing schematically the structure of a sequence parser forming part of the embodiment of Figure 2;
  • Figure 6 shows schematically the content of a field within a store forming part of Figure 5;
  • Figure 7 shows schematically the content of a buffer forming part of Figure 5;
  • Figure 8 is a flow diagram showing schematically the operation of the sequence parser of Figure 5;
  • Figure 9 is a block diagram indicating the structure of a pause detector forming part of the embodiment of Figure 2;
  • Figure 10 is a block diagram showing schematically a part of the structure of Figure 9 in greater detail;
  • Figure 11 is a flow diagram illustrating the operation of an averager forming part of Figure 10;
  • Figure 12 is a flow diagram illustrating the process of deriving a signal to noise ratio by the apparatus of Figure 10
  • Figure 13 is a flow diagram illustrating the process of forming a measure of signal variance by the apparatus of Figure 10;
  • Figure 14 is a block diagram showing in greater detail a part of the structure of Figure 10;
  • Figure 15 is a block diagram showing in greater detail the combination logic forming part of Figure 10;
  • Figure 16 is a diagram of energy and averaged energy of a speech signal over time and indicating the correspondence with signal frames;
  • Figure 17 is a flow diagram illustrating the operation of a rejector forming part of Figure 2;
  • Figure 18 is a flow diagram corresponding to Figure 11 illustrating the process of deriving an average in a second embodiment of the invention
  • Figure 19 is a diagram of energy and averaged energy against time in the embodiment of Figure 18, and corresponds to Figure 16.
  • a telecommunications system including speech recognition generally comprises a microphone 1 typically forming part of a telephone handset, a telecommunications network (typically a public switched telecommunications network (PSTN)) 2, a recognition processor 3, connected to receive a voice signal from the network 2, and a utilising apparatus 4 connected to the recognition processor 3 and arranged to receive therefrom a speech recognition signal, indicating recognition or otherwise of particular words or phrases, and to take action in response thereto.
  • the utilising apparatus 4 may be a remotely operated banking terminal for effecting banking transactions.
  • the utilising apparatus 4 will generate an auditory response to the speaker, transmitted via the network 2 to a loudspeaker 5 typically forming a part of the subscriber handset.
  • a speaker speaks into the microphone 1 and an analog speech signal is transmitted from the microphone 1 into the network 2 to the recognition processor 3, where the speech signal is analysed and a signal indicating identification or otherwise of a particular word or phrase is generated and transmitted to the utilising apparatus 4, which then takes appropriate action in the event of recognition of an expected word or phrase.
  • the recognition processor 3 may be arranged to recognise digits 0 to 9, "yes” and “no” so as to be able to recognise personal identification numbers and a range of command words for initiating particular actions (for example, requesting statements or particular services) .
  • the recognition processor 3 comprises an input 31 for receiving speech in digital form (either from a digital network or from an analog to digital converter) , a frame processor 32 for partitioning the succession of digital samples into frames of contiguous samples; a feature extractor 33 for generating from the frames of samples a corresponding feature vector; a classifier 34 receiving the succession of feature vectors and operating on each with the plurality of models corresponding to different words, phonemes or phrases to generate recognition results; and a parser 35 which is arranged to receive the classification results from the classifier 34 and to determine the word to which the sequence of classifier outputs indicates the greatest similarity.
  • a recognition rejector 36 arranged to reject recognition of a word recognised by the parser 35 if recognition is unreliable, and a pause detector 37, arranged to detect the pause following the end of a word to enable the parser 35 to output a word recognition signal.
  • the word recognition signal from the parser 35, or a rejection signal from the rejector 36, is output to a control signal output 38, for use in controlling the utilising apparatus 4.
  • the frame generator 32 is arranged to receive speech samples at a rate of, for example, 8,000 samples per second, and to form frames comprising 256 contiguous samples, at a frame rate of 1 frame every 16ms.
  • each frame is windowed (i.e. the samples towards the edge of the frame are multiplied by predetermined weighting constants) using, for example, a Hamming window to reduce spurious artifacts, generated by the frame edges.
  • the frames are overlapping (for example by 50%) so as to ameliorate the effects of the windowing.
  • the feature extractor 33 receives frames from the frame generator 32 and generates, in each case, a set or vector of features.
  • the features may, for example, comprise cepstral coefficients (for example, LPC cepstral coefficients or mel frequency cepstral coefficients as described in "On the Evaluation of Speech Recognisers and Data Bases using a Reference System", Chollet & Gagnoulet, 1982 proc. IEEE p2026) , or differential values of such coefficients comprising, for each coefficient, the difference between the coefficient and the corresponding coefficient value in the preceding frame, as described in "On the use of Instantaneous and Transitional Spectral Information in Speaker Recognition", Soong _. Rosenberg, 1988 IEEE Trans, on Accoustics, Speech and Signal Processing Vol 36 No. 6 p871. Equally, a mixture of several types of feature coefficient may be used.
  • the feature extractor 33 also extracts a value for the energy in each frame (which energy value may, but need not, be one of the feature coefficients used in recognition) .
  • the energy value may be generated as the sum of the squares of the samples of the frame.
  • the feature extractor 33 outputs a frame number, incremented for each successive frame.
  • the frame generator 32 and feature extractor 33 are, in this embodiment, provided by a single suitably programmed digital signal processor (DSP) device (such as the Motorola DSP 56000, the Texas Instruments TMS C 320 or similar device.
  • DSP digital signal processor
  • the classifier 34 comprises a classifying processor 341 and a state memory 342.
  • the state memory 342 comprises a state field 3421, 3422, ...., for each of the plurality of speech states.
  • each word to be recognised by the recognition processor comprises 6 or 8 states, and accordingly 6 or 8 state fields are provided in the state memory 342 for each word to be recognised.
  • Each state field in the state memory 342 comprises data defining a multidimensional Gaussian distribution of feature coefficient values which characterise the state in question. For example, if there are d different feature coefficients, the data characterising a state are a constant C, a set of d feature mean values ⁇ ⁇ _ and a set of d feature deviations, ⁇ -_ ; in other words, a total of 2d + 1 numbers.
  • the classification processor 34 is arranged to read each state field within the memory 342 in turn, and calculate for each, using the current input feature coefficient set, the probability that the input feature set or vector corresponds to the corresponding state. To do so, as shown in Figure 4, the processor 341 is arranged to calculate an equation
  • the state memory 342 may comprise, for each state, several mode fields each corresponding to the state field described above, in which case the classification processor 341 is arranged to calculate for each mode the probability that the input vector corresponds to that mode, and then to sum the modal probabilities (weighted as appropriate) .
  • the output of the classification processor 341 is a plurality of state probabilities, one for each state in the state memory 342, indicating the likelihood that the input feature vector corresponds to each state.
  • the classifying processor 341 may be a suitably programmed digital signal processing (DSP) device, may in particular be the same digital signal processing device as the feature extractor 33.
  • DSP digital signal processing
  • the parser 35 in this embodiment comprises a state sequence memory 352, a parsing processor 351, and a parser output buffer 354. Also provided is a state probability memory 353 which stores, for each frame processed, the state probabilities output by the probability processor 341.
  • the state sequence memory 352 comprises a plurality of state sequence fields 3521, 3522, ...., each corresponding to a noise-word-noise sequence to be recognised (and one corresponding to a noise- only sequence) .
  • Each state sequence in the state sequence memory 352 comprises, as illustrated in Figure 6, a number of states P x , P 2 , P N (where N is 6 or 8) and, for each state, two probabilities; a repeat probability (P ⁇ ) and a transition probability to the following state ( i 2 ) •
  • the first and final states are noise states.
  • the observed sequence of states associated with a series of frames may therefore comprise several repetitions of each state ? ⁇ _ in each state sequence model 3521 etc; for example:
  • frame number 3 the observed sequence will move from the initial, noise, state to the next, speech, state; this transition marks the start of the word to be recognised.
  • frame Z the sequence reaches the last state P n corresponding to noise or silence following the end of the word to be recognised. Frame Z therefore corresponds to the end of the word to be recognised.
  • the parsing processor 351 is arranged to read, at each frame, the state probabilities output by the probability processor 341 and the previous stored state probabilities in the state probability memory 353 and to calculate the most likely path of states to date over time, and to compare this with each of the state sequences stored in the state sequence memory 352.
  • the calculation employs the well known hidden Markov model method described in the above referenced Cox paper.
  • the HMM processing performed by the parsing processor 351 uses the well known Viterbi algorithm.
  • the parsing processor 351 may, for example, be a microprocessor such as the Intel ( TM ) i-486 ( TM ) microprocessor or the Motorola ( TM ) 68000 microprocessor, or may alternatively be a DSP device (for example, the same DSP device as is employed for any of the preceding processors) .
  • a probability score is output by the parser processor 351 at each frame of input speech.
  • the identity of the most likely state sequence (and hence word recognised) may well change during the duration of the utterance by the speaker.
  • the parser output buffer 354 comprises a plurality of fields 3541, 3542, ... each corresponding to a word to be recognised (and one which corresponds to a noise-only sequence) .
  • Each field as shown illustratively in Figure 7, comprises a probability score S indicating, for the current frame, the likelihood of the corresponding word being present, and two frame numbers; a first (sp_st) which indicates the first frame of the word in the noise-word-noise observed sequence of frames; and a second (sp_end) which indicates the last frame of the word.
  • the states in the observed sequence comprise initial noise and after sp_end, the states in the observed sequence correspond to terminal noise.
  • the frame numbers in each of the fields 3541, 3542, .... differ from one another.
  • the pause detector 37 comprises a signal based detector 370 and a model based detector 375.
  • the signal based detector 370 is connected to the feature extractor 33, to receive a parameter extracted from the speech signal.
  • the parameter is the frame energy, or some parameter based on the frame energy.
  • the model based detector 375 is connected to the parser 35, to receive an indication of the current best state sequence. Specifically, the model based detector 375 is arranged to read from the parser output buffer 354 the frame number (sp_end) of the start of final noise states, if any, in the current most probable state sequence and to subtract this from the current frame number to find the length of the period following the end of the word which is currently assumed to be recognised.
  • the output of the signal based pause detector 370 and the model based pause detector 375 are combined by logic 378 to generate a pause detection signal at an output 379.
  • the signal based pause detector 370 comprises a running averager 371 which maintains a running average energy level over a number of preceding energy values; a signal to noise ratio (SNR) detector 372 and a noise variance (NVR) detector 373, the outputs of which are supplied to be combined by logic 378. Also provided is a mean energy level buffer 376, connected to the output of the averager 371 to store successive mean energy values corresponding to successive frames.
  • SNR signal to noise ratio
  • NVR noise variance
  • the running averager 371 is arranged schematically to perform the process shown in Figure 11.
  • the energy of the frame is read from the feature extractor 33, and subtracted from a stored running average value to yield the difference value.
  • the difference value is compared with a threshold or step of predetermined absolute value. If the difference lies within +/- the step value, the running average is unaffected, but the value of the step is reduced by setting it equal to the difference divided by a constant factor or, as indicated in Figure 11, a first constant factor (upfactor) for a positive difference from the running mean and a second factor
  • the running average is incremented or decremented by the step value depending upon the size of the difference.
  • the step value is then updated as before.
  • the effect of this process is as follows. Firstly, there is a smoothing of the energy value by the process of maintaining a running average.
  • the instantaneous running average represents a smoothed value of the energy level of the current frame taking some account of past energy levels .
  • the presence of the threshold test introduces a non-linearity into the process such that high positive or negative energy levels, differing substantially from the previous average energy level, are at first ignored.
  • the threshold is subsequently enlarged so that if the high energy level is maintained, it will eventually fall within the threshold and have an effect on the running mean.
  • a short lived high energy level due to a noise spike will have little or no effect on the running mean energy level, because of the threshold stage.
  • a genuinely high energy level due, for example, to a transition to speech will eventually affect the running mean energy level.
  • the threshold is thus adaptive over time so that where incoming energy levels correspond closely to the current mean, the threshold or step level progressively shrinks to a low value, but where incoming energy levels diverge from the mean, the threshold remains initially low but then expands.
  • the averager 371 is thus acting to maintain an average level which behaves somewhat like a running median.
  • the SNR Detector 372 is arranged, at each frame, to input the frame numbers which the parser 35 has identified as the beginning and end frames of the currently most probable recognised word, and to read the average energy level buffer 376, to determine a representative energy level over the frames currently identified as speech and a representative energy level over the frames current represented as noise.
  • the representative measures comprise the mean running energy level running over the noise segments and the peak average energy level over the speech segment .
  • the operation of the SNR detector 372 is shown in Figure 12.
  • the SNR pause detector 372 If the calculated signal to noise ratio value, SNR, is greater than a predetermined threshold, the SNR pause detector 372 outputs a signal indicating that a pause has occurred
  • the SNR measure is a useful identifier of whether a correct word ending has been identified. This is partly because an erroneous recognition by the parser 35 of the start and end (and, indeed, the identity) of a word may result in speech frames being included in those frames used to calculate the mean noise level, and hence reducing the value of the SNR calculated to below the threshold so that a pause is not wrongly identified for this reason.
  • the peak energy level as the characteristic energy level for speech in the SNR calculation, the reverse effect is generally avoided since the peak will generally be unaffected by wrongful identification of the start and end of the word (unless a completely erroneous recognition has taken place) .
  • the NVR Detector 373 is arranged to read the last Nl (where Nl is a predetermined constant) running average energy levels from the buffer 376, and to find the minimum and maximum values, and to calculate the ratio between the minimum and the maximum values. This ratio indicates the amount of variation of the energy level over the most recent Nl frames. If the level of variation is compared with the threshold; a high level of variation indicates the possibility that the preceding Nl frames include some speech, whereas a low level of variation compared to a predetermined threshold indicates that the last Nl frames are likely to contain only noise, and consequently the NVR detector 373 outputs a pause detection signal.
  • the ratio may under some circumstances correspond to division by a very small number. Accordingly, to avoid singularities in calculation, where the minimum average energy falls below a predetermined threshold level (for example, unity) then the ratio is calculated between the maximum and the predetermined level, rather than between the maximum and the minimum. Other measures of the variance (for example, the difference between the maximum and minimum) could be employed, however the ratio is preferred since it takes account of gross variations in overall signal strength.
  • a predetermined threshold level for example, unity
  • the model based pause detector comprises, as shown in Figure 14, first and second time out detectors 376a, 376b arranged to input from the parser 35 the frame number of the currently identified end of speech/start of end noise, and to test the difference N between this frame and the present frame against a first, relatively short, threshold Nl and a second, relatively long, threshold N2.
  • Nl is selected to be on the order of the length of a short gap within a word (i.e. 20 - 60 frames, and conveniently the same length as the test used in the NVR detector 373) and N2 is selected to be substantially longer (i.e. on the order of half a second) .
  • noise score tester 377 which is arranged to read from the parser 35 the likelihood score for the end noise corresponding to the current most likely state sequence, and to test the score against a predetermined threshold, and to output a 'pause detected' signal in the event that the noise score exceeds the threshold.
  • a third time out detector 376c is provided, which tests the total number of frames to date (current frame number) T against a long time out N3, so as to terminate the recognition process after N3 frames if no end of speech has
  • a pause is detected either after the expiry of a long timeout (N3 frames) from the start of recognition, or after a relatively long time out (N2 frames) after the onset of noise, or after a relatively short time out (Nl frames) following which the noise score is high, the signal to noise ratio is high and the noise variance is low.
  • N3 frames a long timeout
  • N2 frames relatively long time out
  • Nl frames relatively short time out
  • Figure 16 illustrates the energy and average energy RM(t) over a word.
  • the rejector 36 is arranged, after the operation of the pause detector 37, to test the level of confidence of the identification of a word by the parser 35. If the identification is suspect, it is rejected. If the identification is tentative the rejector.36 issues a "query" signal which enables the utilising apparatus 4 to, for example, initiate a confirmatory dialogue by synthesising a phrase such as "did you say .... (the identified word) " or to ask the user to repeat the word. Referring to Figure 17, the general operation of the rejector 36 is as follows.
  • the rejector tests whether the signal corresponds to the detection of silence or noise alone. This occurs when the most likely sequence detected by the parser 35 corresponds to a sequence containing only noise states.
  • Silence is also detected by testing whether the SNR calculated by the SNR detector 372 lies below a very low threshold. In either case, the rejector indicates that no word (silence) has been detected, provided the test performed by the detector 376a is also met.
  • the rejector performs rejection tests (discussed in greater detail below) and tests the results against relatively loose thresholds. If the relatively loose thresholds are not met, the identification is rejected. If the relatively loose thresholds are met, the test is repeated against relatively tight thresholds. If the relatively tight thresholds are met, acceptance of the identified word is indicated. If the tight thresholds are not met, a query output is generated, to enable the utilising apparatus to query the user.
  • the tests performed by the rejector comprise:
  • the rejector 36 can either accept a word, in which case the output of the parser 35 is passed to the output 38; or indicate that silence is present (i.e. no word is present) , in which a signal identifying silence is passed to the output 38; or reject or query the identification of a word by the parser 35, in which case the output of the parser 35 is inhibited and a corresponding "reject" or "query” control signal is passed to the output 38 to enable action by the utilising apparatus 4.
  • the feature generator 33 is arranged to compare a newly generated set of feature coefficients with the last - output set of feature coefficients, and only to output a new set of feature coefficients when the overall difference from the earlier set is greater than a predetermined threshold.
  • the distance may be the sum of absolute differences or "city block” distance measure, or any other convenient measure.
  • this technique can substantially reduce the amount of calculation required by the classifier 34 and parser 35 by, for example, on the order of 60%. Furthermore, since the HMM process makes an assumption that subsequent states are independent of each other, this embodiment may under some circumstances increase the validity of this assumption since it causes each successive set of coefficients to differ substantially from its predecessor. In this case, it is found that the operation of the classifier 34 and parser 35 are not substantially altered. However, the operation of the signal based pause detector 370, specifically the running averager 371, are altered as the average needs to take account of the duration of the periods between successive frames.
  • the feature extractor 33 generates, and supplies to the pause detector 37, a number N(t) associated with each frame, which indicates the number of frames between that frame and the last frame output by the feature generator 33.
  • the feature extractor 33 also accumulates the energy of each frame, so as to supply a cumulative energy E(t) at each set of feature coefficients which are output, which corresponds to the sum of the energy giving rise to that set of coefficients and the energies of all the other frames between that frame and the previous frame output by the feature extractor 33.
  • the averager 371 reads the cumulative energy E(t) and the number of frames N(t) represented by a VFR frame, and then generates the average energy for each intervening frame by dividing E(t) by N(t) .
  • the averager then, essentially, simulates the effect of receiving N(t) successive frames each having average energy, and increments or decrements the running average accordingly.
  • the final averaged energy level RM(t) calculated for the VFR frame is found by averaging the N successive running averages by accumulating the running averages and then normalising by N(t) at the end of the calculation.
  • the numbers stored in the output buffer 374 comprise the values RM(t) for each of the frames of the feature coefficients emitted at a variable rate by the coefficient generator 33, which correspond to the average level of the signal frames preceding the current frame.
  • the minimum and maximum energy levels are less clearly defined than the first embodiment because the process of cumulating energy of preceding frames carried out in the feature generator 33 acts to smooth sharp peaks or dips in the energy level of the input speech signal.
  • the averager 371 it would of course be possible instead for the averager 371 to receive and process each of the energy levels from each of the signal frames received by the feature generator 33, regardless of whether or not those frames give rise to the outputting of a feature vector for recognition. However, this would require further calculation and buffering.
  • the pause tests calculated by the detectors 376a, 376b are calculated so as to take account of the variable rate at which coefficient vectors are generated by maintaining a current frame number calculated by accumulating the numbers of omitted frames N(t) and using this to calculate the time since the end of speech N.
  • Figure 19 illustrates the energy, and average energy RM(t) , over a word.
  • a pause detector in a continuous speech recogniser which actively examines the speech signal, it is possible to provide a rapid recognition of input words, phrases or sentences.
  • the pause detector examine parameters which are separate from the speech/noise model, assumed by the speech detector, greater robustness is ensured.
  • energy based measures can be particularly effective in discriminating between speech and noise, in particular, a test of the difference between the signal level and the noise level (for example, a measure of the signal to noise ratio) generated on the assumption that the noise- speech-noise model used by the recogniser is correct is found to be an effective means of validating the correctness of that assumption. More particularly, a signal to noise ratio calculated between a peak value over a speech period and an average value over a noise period is found to be effective.
  • an averaged or smoothed measure of the signal energy in particular, a running average measure and, more particularly, a non-linear average which provides some filtering of noise spikes is preferred.
  • the algorithm may preferably be arranged approximately to track the median rather than the mean of the energy of the signal.
  • the algorithm may be arranged to increment or decrement the running average by a predetermined amount, and the predetermined amount is preferably adapted in dependence upon the difference between the input energy level and the running average.
  • the use of a measure of the variation of signal energy (and, more specifically, variation of the smooth and averaged signal energy) is found to be a good discriminator allowing the determination of whether only noise is present; in particular, a measure of the ratio between peak energy and minimum energy is generally low if only noise is present. Accordingly, this test can be employed to validate the noise- speech-noise model generated by the recognition process.
  • the above tests are advantageously, but not necessarily, combined with tests based on the recogniser output itself, such as a test of the score generated by the recognition of noise, and a test of the length of time since the onset of recognised noise.
  • the present invention is equally applicable to connected-word recognition.
  • the state sequence models would represent sequences of noise-wordl-word2-....- wordN-noise, and the SNR and noise variance tests would preferably be responsive only to the noise after the end of speech point.
  • speech recognition has been described, use of the same techniques in relation to other types of recognition (for example speaker recognition or verification) is not excluded .

Landscapes

  • Engineering & Computer Science (AREA)
  • Acoustics & Sound (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Telephonic Communication Services (AREA)
  • Indicating And Signalling Devices For Elevators (AREA)
  • Character Discrimination (AREA)
  • Machine Translation (AREA)

Abstract

Système de reconnaissance comprenant: des moyens d'entrée servant à recevoir un signal vocal; des moyens de traitement de reconnaissance servant à traiter le signal vocal, afin d'indiquer sa similitude à des configurations prédéterminées à identifier, lesdits moyens de traitement de reconnaissance étant conçus de façon répétée afin de diviser le signal vocal en une partie contenant une configuration et en des parties de bruit ou de silence précédant et suivant lesdites parties contenant des configurations, ainsi que d'identifier une configuration correspondant à ladite partie contenant une configuration; des moyens de sortie servant à émettre un signal de reconnaissance indiquant la reconnaissance d'une desdites configurations, charactérisée par des moyens de détection de pause servant à détecter la partie de bruit ou de silence suivant la partie contenant une configuration, ainsi que des moyens, réagissant à ladite détection, conçus pour émettre un signal identifiant la configuration correspondant normalement à la partie de configuration vers les moyens de sortie. L'invention concerne également des moyens de rejet fonctionnant de façon similaire.
PCT/GB1994/000630 1993-03-25 1994-03-25 Reconnaissance vocale a detection de pause WO1994022131A2 (fr)

Priority Applications (6)

Application Number Priority Date Filing Date Title
AU64330/94A AU6433094A (en) 1993-03-25 1994-03-25 Speech recognition with pause detection
DE69421911T DE69421911T2 (de) 1993-03-25 1994-03-25 Spracherkennung mit pausedetektion
US08/525,730 US5848388A (en) 1993-03-25 1994-03-25 Speech recognition with sequence parsing, rejection and pause detection options
EP94912002A EP0691022B1 (fr) 1993-03-25 1994-03-25 Reconnaissance vocale a detection de pause
JP52084194A JP3691511B2 (ja) 1993-03-25 1994-03-25 休止検出を行う音声認識
CA002158849A CA2158849C (fr) 1993-03-25 1994-03-25 Reconnaissance vocale a detection des silences

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
EP93302302.0 1993-03-25
EP93302302 1993-03-25
EP93302541.3 1993-03-31
EP93302541 1993-03-31

Publications (2)

Publication Number Publication Date
WO1994022131A2 true WO1994022131A2 (fr) 1994-09-29
WO1994022131A3 WO1994022131A3 (fr) 1995-01-12

Family

ID=26134232

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/GB1994/000630 WO1994022131A2 (fr) 1993-03-25 1994-03-25 Reconnaissance vocale a detection de pause

Country Status (9)

Country Link
US (1) US5848388A (fr)
EP (2) EP0691022B1 (fr)
JP (1) JP3691511B2 (fr)
AU (1) AU6433094A (fr)
CA (1) CA2158849C (fr)
DE (2) DE69432570T2 (fr)
ES (1) ES2141824T3 (fr)
SG (1) SG93215A1 (fr)
WO (1) WO1994022131A2 (fr)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1747553A1 (fr) * 2004-05-12 2007-01-31 Nokia Corporation Detection de fin d'enonciation dans un systeme de reconnaissance vocale
EP1517299A3 (fr) * 1997-04-30 2012-08-29 Nippon Hoso Kyokai Méthode et système pour la détection d'un intervalle de parole, et méthode et système pour modifier le débit de parole utilisant la méthode et le système pour la détection d'un intervalle de parole
WO2018063652A1 (fr) * 2016-09-27 2018-04-05 Intel Corporation Détecteur adaptatif de fin de parole
US11145305B2 (en) 2018-12-18 2021-10-12 Yandex Europe Ag Methods of and electronic devices for identifying an end-of-utterance moment in a digital audio signal

Families Citing this family (52)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB9620082D0 (en) 1996-09-26 1996-11-13 Eyretel Ltd Signal monitoring apparatus
GB9625284D0 (en) * 1996-12-04 1997-01-22 Canon Kk A data processing method and apparatus for identifying a classification to which data belongs
US5930748A (en) * 1997-07-11 1999-07-27 Motorola, Inc. Speaker identification system and method
US6374219B1 (en) * 1997-09-19 2002-04-16 Microsoft Corporation System for using silence in speech recognition
US6006182A (en) * 1997-09-22 1999-12-21 Northern Telecom Limited Speech recognition rejection method using generalized additive models
US6718302B1 (en) * 1997-10-20 2004-04-06 Sony Corporation Method for utilizing validity constraints in a speech endpoint detector
JP3075250B2 (ja) * 1998-03-04 2000-08-14 日本電気株式会社 話者認識方法及び装置
DE19824353A1 (de) * 1998-05-30 1999-12-02 Philips Patentverwaltung Vorrichtung zur Verifizierung von Signalen
DE19824354A1 (de) * 1998-05-30 1999-12-02 Philips Patentverwaltung Vorrichtung zur Verifizierung von Signalen
US6324509B1 (en) * 1999-02-08 2001-11-27 Qualcomm Incorporated Method and apparatus for accurate endpointing of speech in the presence of noise
DE19939102C1 (de) * 1999-08-18 2000-10-26 Siemens Ag Verfahren und Anordnung zum Erkennen von Sprache
GB2355833B (en) * 1999-10-29 2003-10-29 Canon Kk Natural language input method and apparatus
US6910035B2 (en) * 2000-07-06 2005-06-21 Microsoft Corporation System and methods for providing automatic classification of media entities according to consonance properties
US7035873B2 (en) 2001-08-20 2006-04-25 Microsoft Corporation System and methods for providing adaptive media property classification
US20020042709A1 (en) * 2000-09-29 2002-04-11 Rainer Klisch Method and device for analyzing a spoken sequence of numbers
US20030023439A1 (en) * 2001-05-02 2003-01-30 Gregory Ciurpita Method and apparatus for automatic recognition of long sequences of spoken digits
US20040104062A1 (en) * 2002-12-02 2004-06-03 Yvon Bedard Side panel for a snowmobile
EP1363271A1 (fr) 2002-05-08 2003-11-19 Sap Ag Méthode et système pour le traitement et la mémorisation du signal de parole d'un dialogue
DE10220524B4 (de) 2002-05-08 2006-08-10 Sap Ag Verfahren und System zur Verarbeitung von Sprachdaten und zur Erkennung einer Sprache
US7356466B2 (en) * 2002-06-28 2008-04-08 Samsung Electronics Co., Ltd. Method and apparatus for performing observation probability calculations
US20040044517A1 (en) * 2002-08-30 2004-03-04 Robert Palmquist Translation system
US7539086B2 (en) * 2002-10-23 2009-05-26 J2 Global Communications, Inc. System and method for the secure, real-time, high accuracy conversion of general-quality speech into text
JP4463526B2 (ja) * 2003-10-24 2010-05-19 株式会社ユニバーサルエンターテインメント 声紋認証システム
BRPI0417636A (pt) * 2003-12-16 2007-03-27 Speechgear Inc sistema, método, e, meio legìvel por computador
CN1894685A (zh) * 2003-12-17 2007-01-10 思比驰盖尔公司 翻译工具
US7664642B2 (en) * 2004-03-17 2010-02-16 University Of Maryland System and method for automatic speech recognition from phonetic features and acoustic landmarks
US7558389B2 (en) * 2004-10-01 2009-07-07 At&T Intellectual Property Ii, L.P. Method and system of generating a speech signal with overlayed random frequency signal
US7584098B2 (en) * 2004-11-29 2009-09-01 Microsoft Corporation Vocabulary-independent search of spontaneous speech
US8175877B2 (en) * 2005-02-02 2012-05-08 At&T Intellectual Property Ii, L.P. Method and apparatus for predicting word accuracy in automatic speech recognition systems
EP1708172A1 (fr) * 2005-03-30 2006-10-04 Top Digital Co., Ltd. Système d'identification d'empreintes vocales pour le commerce electronique
KR101116363B1 (ko) * 2005-08-11 2012-03-09 삼성전자주식회사 음성신호 분류방법 및 장치, 및 이를 이용한 음성신호부호화방법 및 장치
US7603275B2 (en) * 2005-10-31 2009-10-13 Hitachi, Ltd. System, method and computer program product for verifying an identity using voiced to unvoiced classifiers
JP4846735B2 (ja) * 2005-12-14 2011-12-28 三菱電機株式会社 音声認識装置
JP4906379B2 (ja) * 2006-03-22 2012-03-28 富士通株式会社 音声認識装置、音声認識方法、及びコンピュータプログラム
EP1933302A1 (fr) * 2006-12-12 2008-06-18 Harman Becker Automotive Systems GmbH Procédé de reconnaissance vocale
US20080221882A1 (en) * 2007-03-06 2008-09-11 Bundock Donald S System for excluding unwanted data from a voice recording
JP5395066B2 (ja) * 2007-06-22 2014-01-22 ヴォイスエイジ・コーポレーション 音声区間検出および音声信号分類ための方法および装置
DE102008039329A1 (de) * 2008-01-25 2009-07-30 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Vorrichtung und Verfahren zur Berechnung von Steuerinformationen für ein Echounterdrückungsfilter und Vorrichtung und Verfahren zur Berechnung eines Verzögerungswerts
WO2010019831A1 (fr) * 2008-08-14 2010-02-18 21Ct, Inc. Modèle de markov caché pour un traitement de la parole avec procédé de mise en pratique
US8838449B2 (en) * 2010-12-23 2014-09-16 Microsoft Corporation Word-dependent language model
US9064492B2 (en) 2012-07-09 2015-06-23 Nuance Communications, Inc. Detecting potential significant errors in speech recognition results
US8924213B2 (en) 2012-07-09 2014-12-30 Nuance Communications, Inc. Detecting potential significant errors in speech recognition results
US9799328B2 (en) * 2012-08-03 2017-10-24 Veveo, Inc. Method for using pauses detected in speech input to assist in interpreting the input during conversational interaction for information retrieval
US20140365068A1 (en) * 2013-06-06 2014-12-11 Melvin Burns Personalized Voice User Interface System and Method
US9928851B2 (en) * 2013-09-12 2018-03-27 Mediatek Inc. Voice verifying system and voice verifying method which can determine if voice signal is valid or not
US10832005B1 (en) 2013-11-21 2020-11-10 Soundhound, Inc. Parsing to determine interruptible state in an utterance by detecting pause duration and complete sentences
US9311932B2 (en) * 2014-01-23 2016-04-12 International Business Machines Corporation Adaptive pause detection in speech recognition
KR102446392B1 (ko) * 2015-09-23 2022-09-23 삼성전자주식회사 음성 인식이 가능한 전자 장치 및 방법
US9984689B1 (en) * 2016-11-10 2018-05-29 Linearhub Apparatus and method for correcting pronunciation by contextual recognition
US10636421B2 (en) 2017-12-27 2020-04-28 Soundhound, Inc. Parse prefix-detection in a human-machine interface
KR20210078133A (ko) * 2019-12-18 2021-06-28 엘지전자 주식회사 간투어 검출 모델을 훈련시키기 위한 훈련 데이터 생성 방법 및 장치
US11705125B2 (en) 2021-03-26 2023-07-18 International Business Machines Corporation Dynamic voice input detection for conversation assistants

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4829578A (en) * 1986-10-02 1989-05-09 Dragon Systems, Inc. Speech detection and recognition apparatus for use with background noise of varying levels
EP0474496A2 (fr) * 1990-09-07 1992-03-11 Kabushiki Kaisha Toshiba Appareil de reconnaissance de la parole
EP0518742A1 (fr) * 1991-06-14 1992-12-16 Sextant Avionique Procédé de détection d'un signal utile bruité

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
USRE31188E (en) * 1978-10-31 1983-03-22 Bell Telephone Laboratories, Incorporated Multiple template speech recognition system
DE3066499D1 (en) * 1979-08-13 1984-03-15 Linear Pneumatics Inc Method of removing stuck gaskets and pneumatic impact tool therefor
US4348553A (en) * 1980-07-02 1982-09-07 International Business Machines Corporation Parallel pattern verifier with dynamic time warping
US4761815A (en) * 1981-05-01 1988-08-02 Figgie International, Inc. Speech recognition system based on word state duration and/or weight
US4481593A (en) * 1981-10-05 1984-11-06 Exxon Corporation Continuous speech recognition
US4989248A (en) * 1983-01-28 1991-01-29 Texas Instruments Incorporated Speaker-dependent connected speech word recognition method
US4783804A (en) * 1985-03-21 1988-11-08 American Telephone And Telegraph Company, At&T Bell Laboratories Hidden Markov model speech recognition arrangement
GB2182795B (en) * 1985-11-12 1988-10-05 Nat Res Dev Apparatus and methods for speech analysis
JP2717652B2 (ja) * 1986-06-02 1998-02-18 モトローラ・インコーポレーテッド 連続音声認識システム
JPH0760318B2 (ja) * 1986-09-29 1995-06-28 株式会社東芝 連続音声認識方式
US4837831A (en) * 1986-10-15 1989-06-06 Dragon Systems, Inc. Method for creating and using multiple-word sound models in speech recognition
US4803729A (en) * 1987-04-03 1989-02-07 Dragon Systems, Inc. Speech recognition method
DE3765639D1 (de) * 1987-06-16 1990-11-22 Santex Ag Verfahren zum glaetten und schrumpfen von textiler schlauchware.
US5228110A (en) * 1989-09-15 1993-07-13 U.S. Philips Corporation Method for recognizing N different word strings in a speech signal
JP2870224B2 (ja) * 1991-06-19 1999-03-17 松下電器産業株式会社 音声認識方法
US5388183A (en) * 1991-09-30 1995-02-07 Kurzwell Applied Intelligence, Inc. Speech recognition providing multiple outputs
US5390278A (en) * 1991-10-08 1995-02-14 Bell Canada Phoneme based speech recognition
US5583961A (en) * 1993-03-25 1996-12-10 British Telecommunications Public Limited Company Speaker recognition using spectral coefficients normalized with respect to unequal frequency bands
US5524169A (en) * 1993-12-30 1996-06-04 International Business Machines Incorporated Method and system for location-specific speech recognition
US5621859A (en) * 1994-01-19 1997-04-15 Bbn Corporation Single tree method for grammar directed, very large vocabulary speech recognizer

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4829578A (en) * 1986-10-02 1989-05-09 Dragon Systems, Inc. Speech detection and recognition apparatus for use with background noise of varying levels
EP0474496A2 (fr) * 1990-09-07 1992-03-11 Kabushiki Kaisha Toshiba Appareil de reconnaissance de la parole
EP0518742A1 (fr) * 1991-06-14 1992-12-16 Sextant Avionique Procédé de détection d'un signal utile bruité

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
IBM TECHNICAL DISCLOSURE BULLETIN, vol.34, no.9, February 1992, NEW YORK pages 267 - 269 'Method of endpoint detection' *
IEEE TRANS. ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, vol.29, no.4, August 1981, NEW YORK LAMEL ET AL. 'An improved endpoint detector for isolated word recognition' *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1517299A3 (fr) * 1997-04-30 2012-08-29 Nippon Hoso Kyokai Méthode et système pour la détection d'un intervalle de parole, et méthode et système pour modifier le débit de parole utilisant la méthode et le système pour la détection d'un intervalle de parole
EP1747553A1 (fr) * 2004-05-12 2007-01-31 Nokia Corporation Detection de fin d'enonciation dans un systeme de reconnaissance vocale
EP1747553A4 (fr) * 2004-05-12 2007-11-07 Nokia Corp Detection de fin d'enonciation dans un systeme de reconnaissance vocale
US9117460B2 (en) 2004-05-12 2015-08-25 Core Wireless Licensing S.A.R.L. Detection of end of utterance in speech recognition system
WO2018063652A1 (fr) * 2016-09-27 2018-04-05 Intel Corporation Détecteur adaptatif de fin de parole
US10339918B2 (en) 2016-09-27 2019-07-02 Intel IP Corporation Adaptive speech endpoint detector
US11145305B2 (en) 2018-12-18 2021-10-12 Yandex Europe Ag Methods of and electronic devices for identifying an end-of-utterance moment in a digital audio signal

Also Published As

Publication number Publication date
CA2158849C (fr) 2000-09-05
DE69421911D1 (de) 2000-01-05
JP3691511B2 (ja) 2005-09-07
DE69421911T2 (de) 2000-07-20
AU6433094A (en) 1994-10-11
SG93215A1 (en) 2002-12-17
DE69432570T2 (de) 2004-03-04
WO1994022131A3 (fr) 1995-01-12
ES2141824T3 (es) 2000-04-01
EP0691022B1 (fr) 1999-12-01
EP0962913B1 (fr) 2003-04-23
EP0962913A1 (fr) 1999-12-08
US5848388A (en) 1998-12-08
JPH08508108A (ja) 1996-08-27
CA2158849A1 (fr) 1994-09-29
EP0691022A1 (fr) 1996-01-10
DE69432570D1 (de) 2003-05-28

Similar Documents

Publication Publication Date Title
EP0962913B1 (fr) Reconnaissance de la parole
Wolf Efficient acoustic parameters for speaker recognition
US8566088B2 (en) System and method for automatic speech to text conversion
KR100312919B1 (ko) 화자인식을위한방법및장치
US8036884B2 (en) Identification of the presence of speech in digital audio data
US5339385A (en) Speaker verifier using nearest-neighbor distance measure
Pfau et al. Estimating the speaking rate by vowel detection
US5950157A (en) Method for establishing handset-dependent normalizing models for speaker recognition
US5025471A (en) Method and apparatus for extracting information-bearing portions of a signal for recognizing varying instances of similar patterns
Sahoo et al. Silence removal and endpoint detection of speech signal for text independent speaker identification
US4937870A (en) Speech recognition arrangement
Özaydın Examination of energy based voice activity detection algorithms for noisy speech signals
WO1994022132A1 (fr) Procede et dispositif d'identification de locuteur
JP2797861B2 (ja) 音声検出方法および音声検出装置
KR100940641B1 (ko) 음소레벨 로그우도 비율 분포와 음소 지속시간 분포에 의한단어음색 모델 기반 발화검증 시스템 및 방법
US7292981B2 (en) Signal variation feature based confidence measure
WO1997037345A1 (fr) Traitement de la parole
Aye Speech recognition using Zero-crossing features
Pawar et al. Analysis of FFSR, VFSR, MFSR techniques for feature extraction in speaker recognition: a review
Nickel et al. Robust speaker verification with principal pitch components
Ying et al. Robust voice activity detection based on noise eigenspace
KR950002704B1 (ko) 음성인식 시스템의 유사음성 구분장치 및 구분방법
Arcienega et al. Robust voiced-unvoiced decision associated to continuous pitch tracking in noisy telephone speech.
JPH05249987A (ja) 音声検出方法および音声検出装置
Nickel et al. Optimal pitch bases expansions in speech signal processing

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): AU CA CN FI JP KR NZ US

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): AT BE CH DE DK ES FR GB GR IE IT LU MC NL PT SE

121 Ep: the epo has been informed by wipo that ep was designated in this application
DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
AK Designated states

Kind code of ref document: A3

Designated state(s): AU CA CN FI JP KR NZ US

AL Designated countries for regional patents

Kind code of ref document: A3

Designated state(s): AT BE CH DE DK ES FR GB GR IE IT LU MC NL PT SE

WWE Wipo information: entry into national phase

Ref document number: 2158849

Country of ref document: CA

WWE Wipo information: entry into national phase

Ref document number: 1994912002

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 08525730

Country of ref document: US

WWP Wipo information: published in national office

Ref document number: 1994912002

Country of ref document: EP

WWG Wipo information: grant in national office

Ref document number: 1994912002

Country of ref document: EP